claude-code-app-studio / design
CLAUDE.md40 starsChanged 7 months agoMITView on GitHub
Product design lives here. The directory has three subtrees, each with a distinct owner and a distinct kind of artefact. The product brief at design/prd/00-product-brief.md is the master document. Personas live at design/prd/personas.md. Both are references, not features. Each flow doc has eight required sections: entry points, primary path, alternate paths, error paths, permissions, offline behaviour, exit points, accessibility notes. - design/comps/ — visual comps from visual-design-director. Optional. Many teams keep comps in Figma and link from PRDs instead of…
In this repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- asset-auditSkill
- asset-specSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- bug-triageSkill
- changelogSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-bibleSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- estimateSkill
- extractSkill
- gate-checkSkill
- helpSkill
- hotfixSkill
- launch-checklistSkill
- localizeSkill
- map-systemsSkill
- milestone-reviewSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- prd-reviewSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- prototypeSkill
- qa-planSkill
- quick-designSkill
- regression-suiteSkill
- release-checklistSkill
- retrospectiveSkill
- reverse-documentSkill
- review-all-prdsSkill
- scope-checkSkill
- security-auditSkill
- setup-frameworkSkill
- skill-improveSkill
- skill-testSkill
- smoke-checkSkill
- soak-testSkill
- sprint-planSkill
- sprint-statusSkill
- startSkill
- story-doneSkill
- The first 60 shown.
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 55
Every design artefact follows the collaborative pattern (see docs/COLLABORATIVE-DESIGN-PRINCIPLE.md):
- Distinctive: line 82
Every PRD has a Review section that records gate verdicts:
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design Directory
Product design lives here. The directory has three subtrees, each with a distinct owner and a distinct kind of artefact.
Subtrees
design/prd/
Product Requirements Documents — one per feature. Owned by
product-designer and authored via /prd-create. Every PRD has the 11
required sections defined in .claude/rules/design-docs.md. PRDs use
stable IDs (PRD-AUTH-003) and stable requirement tags (REQ-1,
REQ-2) so other artefacts can cite them.
The product brief at design/prd/00-product-brief.md is the master
document. Personas live at design/prd/personas.md. Both are
references, not features.
design/flows/
User-journey documents — one per flow. Owned by ux-designer and
authored via /flow-create. A flow is a multi-step task the user can
accomplish: sign-in, checkout, create-listing, password-reset.
Each flow doc has eight required sections: entry points, primary path, alternate paths, error paths, permissions, offline behaviour, exit points, accessibility notes.
design/registry/
Canonical names for screens, data models, API endpoints, analytics
events, and feature flags. The registry is the tiebreaker when two PRDs
disagree on a name. See design/registry/README.md for details.
Adjacent Artefacts (Not Subtrees)
design/comps/— visual comps fromvisual-design-director. Optional. Many teams keep comps in Figma and link from PRDs instead of duplicating them in the repo. If you keep them in-repo, organise by feature.design/research/— interview notes, usability test reports. Created byuser-researcher. Stored as plain Markdown with one file per session.design/content/— content strategy assets: voice and tone guide, vocabulary list, banned terms, push notification copy templates. Owned bycontent-strategistandcontent-designer.design/motion/— motion specs and reference clips. Owned bymotion-designer. Includes haptics patterns and audio cues.design/brand/— brand guidelines, logo system, marketing-vs-product alignment. Owned bybrand-director.
These adjacent directories are created on demand. Do not pre-populate them; create them when an artefact lands.
Authoring Protocol
Every design artefact follows the collaborative pattern (see
docs/COLLABORATIVE-DESIGN-PRINCIPLE.md):
- The agent asks clarifying questions.
- The agent presents 2-4 options with trade-offs.
- The user decides.
- The agent drafts a section.
- The user approves.
- The agent writes to disk.
- The agent updates
production/session-state/active.mdand proposes the next section.
Multi-section docs (PRDs, flows) use the incremental writing pattern: write the skeleton first, then write each section as it is approved. The conversation about completed sections can be safely compacted; the decisions are on disk.
Cross-References
PRDs cite ADRs (See ADR-0007 for the session storage decision).
ADRs cite PRDs by TR-ID (Addresses TR-AUTH-001). Stories cite both.
The graph is queryable: /architecture-review produces a traceability
matrix that maps every PRD requirement to at least one ADR and at least
one story.
Review
Every PRD has a Review section that records gate verdicts:
## Review
> **Product Director (PD-PRD)**: APPROVED 2026-05-12
> **Lead Designer (LD-PRD-DESIGN)**: APPROVED 2026-05-13
> **Accessibility (A11Y-AUDIT)**: APPROVED 2026-05-13 — see production/qa/evidence/a11y-prd-auth-003.mdVerdicts on artefacts are the record of approval. Do not rely on chat history.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

